Superior resilience to poisoning and amenability to unlearning in quantum machine learning

Abstract

The reliability of artificial intelligence hinges on the integrity of its training data, a foundation often compromised by noise and corruption. Here, through a comparative study of classical and quantum neural networks on both classical and quantum data, we reveal a fundamental difference in their response to data corruption. We find that classical models exhibit brittle memorization, leading to a failure in generalization. In contrast, quantum models demonstrate remarkable resilience, which is underscored by a phase transition-like response to increasing label noise, revealing a critical point beyond which the model's performance changes qualitatively. We further establish and investigate the field of quantum machine unlearning, the process of efficiently forcing a trained model to forget corrupting influences. We show that the brittle nature of the classical model forms rigid, stubborn memories of erroneous data, making efficient unlearning challenging, while the quantum model is significantly more amenable to efficient forgetting with approximate unlearning methods. Our findings establish that quantum machine learning can possess a dual advantage of intrinsic resilience and efficient adaptability, providing a promising paradigm for the trustworthy and robust artificial intelligence of the future.

9 pages, 4 figures with references and supplemental materials

References in corpus (17)

• Challenges and Opportunities in Quantum Machine Learning
• The quest for a Quantum Neural Network
• Quantum advantage in learning from experiments
• Barren Plateaus in Variational Quantum Computing
• TensorCircuit: a Quantum Software Framework for the NISQ Era
• Experimental quantum adversarial learning with programmable superconducting qubits
• Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines
• A comprehensive review of Quantum Machine Learning: from NISQ to Fault Tolerance
• Towards quantum enhanced adversarial robustness in machine learning
• Understanding quantum machine learning also requires rethinking generalization
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Variational Quantum-Neural Hybrid Eigensolver
• Generative quantum machine learning via denoising diffusion probabilistic models
• Absence of barren plateaus in finite local-depth circuits with long-range entanglement
• Neural network encoded variational quantum algorithms
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Efficient and quantum-adaptive machine learning with fermion neural networks